Serveur d'exploration sur l'OCR

Attention, ce site est en cours de développement !
Attention, site généré par des moyens informatiques à partir de corpus bruts.
Les informations ne sont donc pas validées.

Automatic Diacritic Restoration for Resource-Scarce Languages

Identifieur interne : 000D63 ( Main/Exploration ); précédent : 000D62; suivant : 000D64

Automatic Diacritic Restoration for Resource-Scarce Languages

Auteurs : Guy De Pauw [Belgique] ; W. Wagacha [Kenya] ; Gilles-Maurice De Schryver [Belgique, Afrique du Sud]

Source :

RBID : ISTEX:66FA160FDA9F8DED4864CF1FC631F3ADF72BDB82

Abstract

Abstract: The orthography of many resource-scarce languages includes diacritically marked characters. Falling outside the scope of the standard Latin encoding, these characters are often represented in digital language resources as their unmarked equivalents. This renders corpus compilation more difficult, as these languages typically do not have the benefit of large electronic dictionaries to perform diacritic restoration. This paper describes experiments with a machine learning approach that is able to automatically restore diacritics on the basis of local graphemic context. We apply the method to the African languages of Cilubà, Gĩkũyũ, Kĩkamba, Maa, Sesotho sa Leboa, Tshivenda and Yoruba and contrast it with experiments on Czech, Dutch, French, German and Romanian, as well as Vietnamese and Chinese Pinyin.

Url:
DOI: 10.1007/978-3-540-74628-7_24


Affiliations:


Links toward previous steps (curation, corpus...)


Le document en format XML

<record>
<TEI wicri:istexFullTextTei="biblStruct:series">
<teiHeader>
<fileDesc>
<titleStmt>
<title xml:lang="en">Automatic Diacritic Restoration for Resource-Scarce Languages</title>
<author>
<name sortKey="De Pauw, Guy" sort="De Pauw, Guy" uniqKey="De Pauw G" first="Guy" last="De Pauw">Guy De Pauw</name>
</author>
<author>
<name sortKey="Wagacha, W" sort="Wagacha, W" uniqKey="Wagacha W" first="W." last="Wagacha">W. Wagacha</name>
</author>
<author>
<name sortKey="De Schryver, Gilles Maurice" sort="De Schryver, Gilles Maurice" uniqKey="De Schryver G" first="Gilles-Maurice" last="De Schryver">Gilles-Maurice De Schryver</name>
</author>
</titleStmt>
<publicationStmt>
<idno type="wicri:source">ISTEX</idno>
<idno type="RBID">ISTEX:66FA160FDA9F8DED4864CF1FC631F3ADF72BDB82</idno>
<date when="2007" year="2007">2007</date>
<idno type="doi">10.1007/978-3-540-74628-7_24</idno>
<idno type="url">https://api.istex.fr/document/66FA160FDA9F8DED4864CF1FC631F3ADF72BDB82/fulltext/pdf</idno>
<idno type="wicri:Area/Istex/Corpus">000F95</idno>
<idno type="wicri:Area/Istex/Curation">000F46</idno>
<idno type="wicri:Area/Istex/Checkpoint">000778</idno>
<idno type="wicri:doubleKey">0302-9743:2007:De Pauw G:automatic:diacritic:restoration</idno>
<idno type="wicri:Area/Main/Merge">000D76</idno>
<idno type="wicri:Area/Main/Curation">000D63</idno>
<idno type="wicri:Area/Main/Exploration">000D63</idno>
</publicationStmt>
<sourceDesc>
<biblStruct>
<analytic>
<title level="a" type="main" xml:lang="en">Automatic Diacritic Restoration for Resource-Scarce Languages</title>
<author>
<name sortKey="De Pauw, Guy" sort="De Pauw, Guy" uniqKey="De Pauw G" first="Guy" last="De Pauw">Guy De Pauw</name>
<affiliation wicri:level="4">
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>CNTS - Language Technology Group, University of Antwerp</wicri:regionArea>
<placeName>
<settlement type="city">Anvers</settlement>
<region type="district" nuts="2">Province d'Anvers</region>
</placeName>
<orgName type="university">Université d'Anvers</orgName>
</affiliation>
<affiliation wicri:level="1">
<country wicri:rule="url">Belgique</country>
</affiliation>
</author>
<author>
<name sortKey="Wagacha, W" sort="Wagacha, W" uniqKey="Wagacha W" first="W." last="Wagacha">W. Wagacha</name>
<affiliation wicri:level="1">
<country xml:lang="fr">Kenya</country>
<wicri:regionArea>School of Computing and Informatics, University of Nairobi</wicri:regionArea>
<wicri:noRegion>University of Nairobi</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1">
<country wicri:rule="url">Kenya</country>
</affiliation>
</author>
<author>
<name sortKey="De Schryver, Gilles Maurice" sort="De Schryver, Gilles Maurice" uniqKey="De Schryver G" first="Gilles-Maurice" last="De Schryver">Gilles-Maurice De Schryver</name>
<affiliation wicri:level="1">
<country xml:lang="fr">Belgique</country>
<wicri:regionArea>African Languages and Cultures, Ghent University</wicri:regionArea>
<wicri:noRegion>Ghent University</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1">
<country xml:lang="fr">Afrique du Sud</country>
<wicri:regionArea>Xhosa Department, University of the Western Cape</wicri:regionArea>
<wicri:noRegion>University of the Western Cape</wicri:noRegion>
</affiliation>
<affiliation wicri:level="1">
<country wicri:rule="url">Belgique</country>
</affiliation>
</author>
</analytic>
<monogr></monogr>
<series>
<title level="s">Lecture Notes in Computer Science</title>
<imprint>
<date>2007</date>
</imprint>
<idno type="ISSN">0302-9743</idno>
<idno type="eISSN">1611-3349</idno>
<idno type="ISSN">0302-9743</idno>
</series>
<idno type="istex">66FA160FDA9F8DED4864CF1FC631F3ADF72BDB82</idno>
<idno type="DOI">10.1007/978-3-540-74628-7_24</idno>
<idno type="ChapterID">24</idno>
<idno type="ChapterID">Chap24</idno>
</biblStruct>
</sourceDesc>
<seriesStmt>
<idno type="ISSN">0302-9743</idno>
</seriesStmt>
</fileDesc>
<profileDesc>
<textClass></textClass>
<langUsage>
<language ident="en">en</language>
</langUsage>
</profileDesc>
</teiHeader>
<front>
<div type="abstract" xml:lang="en">Abstract: The orthography of many resource-scarce languages includes diacritically marked characters. Falling outside the scope of the standard Latin encoding, these characters are often represented in digital language resources as their unmarked equivalents. This renders corpus compilation more difficult, as these languages typically do not have the benefit of large electronic dictionaries to perform diacritic restoration. This paper describes experiments with a machine learning approach that is able to automatically restore diacritics on the basis of local graphemic context. We apply the method to the African languages of Cilubà, Gĩkũyũ, Kĩkamba, Maa, Sesotho sa Leboa, Tshivenda and Yoruba and contrast it with experiments on Czech, Dutch, French, German and Romanian, as well as Vietnamese and Chinese Pinyin.</div>
</front>
</TEI>
<affiliations>
<list>
<country>
<li>Afrique du Sud</li>
<li>Belgique</li>
<li>Kenya</li>
</country>
<region>
<li>Province d'Anvers</li>
</region>
<settlement>
<li>Anvers</li>
</settlement>
<orgName>
<li>Université d'Anvers</li>
</orgName>
</list>
<tree>
<country name="Belgique">
<region name="Province d'Anvers">
<name sortKey="De Pauw, Guy" sort="De Pauw, Guy" uniqKey="De Pauw G" first="Guy" last="De Pauw">Guy De Pauw</name>
</region>
<name sortKey="De Pauw, Guy" sort="De Pauw, Guy" uniqKey="De Pauw G" first="Guy" last="De Pauw">Guy De Pauw</name>
<name sortKey="De Schryver, Gilles Maurice" sort="De Schryver, Gilles Maurice" uniqKey="De Schryver G" first="Gilles-Maurice" last="De Schryver">Gilles-Maurice De Schryver</name>
<name sortKey="De Schryver, Gilles Maurice" sort="De Schryver, Gilles Maurice" uniqKey="De Schryver G" first="Gilles-Maurice" last="De Schryver">Gilles-Maurice De Schryver</name>
</country>
<country name="Kenya">
<noRegion>
<name sortKey="Wagacha, W" sort="Wagacha, W" uniqKey="Wagacha W" first="W." last="Wagacha">W. Wagacha</name>
</noRegion>
<name sortKey="Wagacha, W" sort="Wagacha, W" uniqKey="Wagacha W" first="W." last="Wagacha">W. Wagacha</name>
</country>
<country name="Afrique du Sud">
<noRegion>
<name sortKey="De Schryver, Gilles Maurice" sort="De Schryver, Gilles Maurice" uniqKey="De Schryver G" first="Gilles-Maurice" last="De Schryver">Gilles-Maurice De Schryver</name>
</noRegion>
</country>
</tree>
</affiliations>
</record>

Pour manipuler ce document sous Unix (Dilib)

EXPLOR_STEP=$WICRI_ROOT/Ticri/CIDE/explor/OcrV1/Data/Main/Exploration
HfdSelect -h $EXPLOR_STEP/biblio.hfd -nk 000D63 | SxmlIndent | more

Ou

HfdSelect -h $EXPLOR_AREA/Data/Main/Exploration/biblio.hfd -nk 000D63 | SxmlIndent | more

Pour mettre un lien sur cette page dans le réseau Wicri

{{Explor lien
   |wiki=    Ticri/CIDE
   |area=    OcrV1
   |flux=    Main
   |étape=   Exploration
   |type=    RBID
   |clé=     ISTEX:66FA160FDA9F8DED4864CF1FC631F3ADF72BDB82
   |texte=   Automatic Diacritic Restoration for Resource-Scarce Languages
}}

Wicri

This area was generated with Dilib version V0.6.32.
Data generation: Sat Nov 11 16:53:45 2017. Site generation: Mon Mar 11 23:15:16 2024